CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

storybook-upgrade

Use this skill when Storybook exists but needs an upgrade.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./code/lib/claude-plugin/skills/storybook-upgrade/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an exemplary lean, single-purpose skill: it defines a concrete success criterion, gives an executable command for the fallback path, and delegates fast-moving details to the authoritative live doc. The only real gap is an explicit post-upgrade verification step to confirm the 11.0+ end state, plus the absence of an inline command for the standard upgrade path.

DimensionReasoningScore

Conciseness

Three lean paragraphs (~70 words) with zero padding and no explanation of concepts Claude already knows — 'Storybook must end up at 11.0 or later. An 11.0 prerelease (11.0.0-alpha.x) or a canary build (0.0.0-pr-*) also counts.' Every token earns its place, matching 'Lean and efficient; assumes Claude's competence'. The version numbers are the task's target, not incidental time-sensitive content, so no penalty applies.

5 / 5

Actionability

The fallback path is fully executable ('upgrade to the 11.0 alpha with npx storybook@next upgrade') and the success criterion is concrete ('must end up at 11.0 or later'), matching 'Mostly executable guidance; concrete code or commands with minor gaps'. It is not a 5 because the primary upgrade path delegates entirely to an external URL ('Read ... in its entirety') with no inline copy-paste command for the standard case.

4 / 5

Workflow Clarity

The logic is clear: a defined end state ('Storybook must end up at 11.0 or later'), an instruction to read the upgrade guide, and an explicit conditional branch ('If the latest stable release is below 11.0, upgrade to the 11.0 alpha ... instead'), matching 'Clear sequence with most checkpoints present; minor validation gaps'. It is not a 5 because there is no explicit post-upgrade verification step (e.g., how to check the installed Storybook version) to confirm the end state was reached.

4 / 5

Progressive Disclosure

The skill is well under 50 lines with no bundle files, and all content belongs inline; the only pointer is a one-level-deep external URL that is clearly signaled ('Read https://storybook.js.org/docs/releases/upgrading.md in its entirety'). Per the rubric's simple-skill note, this matches the top anchor — no trimming or splitting is warranted at this size.

5 / 5

Total

18

/

20

Passed

Description

57%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description has a clear, explicit trigger condition and targets a highly distinctive niche (Storybook upgrades), but it never states what the skill actually does, and its keyword coverage is limited to two terms with no synonyms or version references. Rewriting it to lead with the capability and broaden trigger phrasing would lift the middle dimensions.

Suggestions

State the 'what' explicitly, e.g., 'Upgrades Storybook installations to 11.0 or later (including alpha/canary builds). Use when Storybook exists but is outdated, or when the user asks to update, migrate, or upgrade Storybook.'

Add natural trigger synonyms such as 'update Storybook', 'migrate Storybook', and 'Storybook is out of date / behind the latest version' so the skill fires on phrasings users actually say.

Mention concrete version cues (e.g., 'Storybook 11', 'storybook@next') in the description to strengthen both specificity and trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ('Storybook') and one concrete action ('upgrade'), matching 'Names domain and 1-2 concrete actions, but not comprehensive'. It is above a score of 2 because 'upgrade' is a specific action rather than generic handling like 'Processes PDF files', but below 4 because only one action is named and details like the target version are absent.

3 / 5

Completeness

The 'when' is explicit ('when Storybook exists but needs an upgrade'), but the 'what' is only weakly implied through the word 'upgrade' inside the when-clause rather than stated as a capability (e.g., 'Upgrades Storybook projects to 11.0 or later'). This sits between anchor 2 ('only when present without what') and anchor 4 (both present with when improvable): the what is discernible but not explicit.

3 / 5

Trigger Term Quality

'Storybook' and 'upgrade' are relevant natural keywords, but common variations users would say — 'update Storybook', 'migrate Storybook', 'Storybook is out of date', or version references like 'Storybook 11' — are missing, matching 'Some relevant keywords but missing common variations or synonyms'. It is not a 4 because coverage is thin beyond those two terms.

3 / 5

Distinctiveness Conflict Risk

'Storybook' is a specific named tool with a distinct action ('upgrade'), giving a clear niche with minimal conflict risk against other skills. It fully matches the anchor 'Clear niche with distinct triggers; minimal conflict risk' and is not below 5 since no broader overlap terms appear.

5 / 5

Total

14

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

storybookjs/storybook

Path

code/lib/claude-plugin/skills/storybook-upgrade/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.